“a2df17dc0e83d755bafc7c8874d9a9bc775adf82”上不存在“tests/ocr_det_server_params.txt”
ocr_reader.py 15.7 KB
Newer Older
L
LDOUBLEV 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import cv2
import copy
import numpy as np
import math
import re
import sys
import argparse
import string
from copy import deepcopy


class DetResizeForTest(object):
    def __init__(self, **kwargs):
        super(DetResizeForTest, self).__init__()
        self.resize_type = 0
        if 'image_shape' in kwargs:
            self.image_shape = kwargs['image_shape']
            self.resize_type = 1
        elif 'limit_side_len' in kwargs:
            self.limit_side_len = kwargs['limit_side_len']
            self.limit_type = kwargs.get('limit_type', 'min')
T
add qps  
tink2123 已提交
36
        elif 'resize_short' in kwargs:
L
LDOUBLEV 已提交
37 38
            self.limit_side_len = 736
            self.limit_type = 'min'
T
add qps  
tink2123 已提交
39 40 41
        else:
            self.resize_type = 2
            self.resize_long = kwargs.get('resize_long', 960)
L
LDOUBLEV 已提交
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435

    def __call__(self, data):
        img = deepcopy(data)
        src_h, src_w, _ = img.shape

        if self.resize_type == 0:
            img, [ratio_h, ratio_w] = self.resize_image_type0(img)
        elif self.resize_type == 2:
            img, [ratio_h, ratio_w] = self.resize_image_type2(img)
        else:
            img, [ratio_h, ratio_w] = self.resize_image_type1(img)

        return img

    def resize_image_type1(self, img):
        resize_h, resize_w = self.image_shape
        ori_h, ori_w = img.shape[:2]  # (h, w, c)
        ratio_h = float(resize_h) / ori_h
        ratio_w = float(resize_w) / ori_w
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        return img, [ratio_h, ratio_w]

    def resize_image_type0(self, img):
        """
        resize image to a size multiple of 32 which is required by the network
        args:
            img(array): array with shape [h, w, c]
        return(tuple):
            img, (ratio_h, ratio_w)
        """
        limit_side_len = self.limit_side_len
        h, w, _ = img.shape

        # limit the max side
        if self.limit_type == 'max':
            if max(h, w) > limit_side_len:
                if h > w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.
        else:
            if min(h, w) < limit_side_len:
                if h < w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.
        resize_h = int(h * ratio)
        resize_w = int(w * ratio)

        resize_h = int(round(resize_h / 32) * 32)
        resize_w = int(round(resize_w / 32) * 32)

        try:
            if int(resize_w) <= 0 or int(resize_h) <= 0:
                return None, (None, None)
            img = cv2.resize(img, (int(resize_w), int(resize_h)))
        except:
            print(img.shape, resize_w, resize_h)
            sys.exit(0)
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)
        # return img, np.array([h, w])
        return img, [ratio_h, ratio_w]

    def resize_image_type2(self, img):
        h, w, _ = img.shape

        resize_w = w
        resize_h = h

        # Fix the longer side
        if resize_h > resize_w:
            ratio = float(self.resize_long) / resize_h
        else:
            ratio = float(self.resize_long) / resize_w

        resize_h = int(resize_h * ratio)
        resize_w = int(resize_w * ratio)

        max_stride = 128
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)

        return img, [ratio_h, ratio_w]


class BaseRecLabelDecode(object):
    """ Convert between text-label and text-index """

    def __init__(self, config):
        support_character_type = [
            'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean',
            'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc',
            'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr',
            'ne', 'EN'
        ]
        character_type = config['character_type']
        character_dict_path = config['character_dict_path']
        use_space_char = True
        assert character_type in support_character_type, "Only {} are supported now but get {}".format(
            support_character_type, character_type)

        self.beg_str = "sos"
        self.end_str = "eos"

        if character_type == "en":
            self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
            dict_character = list(self.character_str)
        elif character_type == "EN_symbol":
            # same with ASTER setting (use 94 char).
            self.character_str = string.printable[:-6]
            dict_character = list(self.character_str)
        elif character_type in support_character_type:
            self.character_str = ""
            assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
                character_type)
            with open(character_dict_path, "rb") as fin:
                lines = fin.readlines()
                for line in lines:
                    line = line.decode('utf-8').strip("\n").strip("\r\n")
                    self.character_str += line
            if use_space_char:
                self.character_str += " "
            dict_character = list(self.character_str)

        else:
            raise NotImplementedError
        self.character_type = character_type
        dict_character = self.add_special_char(dict_character)
        self.dict = {}
        for i, char in enumerate(dict_character):
            self.dict[char] = i
        self.character = dict_character

    def add_special_char(self, dict_character):
        return dict_character

    def decode(self, text_index, text_prob=None, is_remove_duplicate=False):
        """ convert text-index into text-label. """
        result_list = []
        ignored_tokens = self.get_ignored_tokens()
        batch_size = len(text_index)
        for batch_idx in range(batch_size):
            char_list = []
            conf_list = []
            for idx in range(len(text_index[batch_idx])):
                if text_index[batch_idx][idx] in ignored_tokens:
                    continue
                if is_remove_duplicate:
                    # only for predict
                    if idx > 0 and text_index[batch_idx][idx - 1] == text_index[
                            batch_idx][idx]:
                        continue
                char_list.append(self.character[int(text_index[batch_idx][
                    idx])])
                if text_prob is not None:
                    conf_list.append(text_prob[batch_idx][idx])
                else:
                    conf_list.append(1)
            text = ''.join(char_list)
            result_list.append((text, np.mean(conf_list)))
        return result_list

    def get_ignored_tokens(self):
        return [0]  # for ctc blank


class CTCLabelDecode(BaseRecLabelDecode):
    """ Convert between text-label and text-index """

    def __init__(
            self,
            config,
            #character_dict_path=None,
            #character_type='ch',
            #use_space_char=False,
            **kwargs):
        super(CTCLabelDecode, self).__init__(config)

    def __call__(self, preds, label=None, *args, **kwargs):
        preds_idx = preds.argmax(axis=2)
        preds_prob = preds.max(axis=2)
        text = self.decode(preds_idx, preds_prob, is_remove_duplicate=True)
        if label is None:
            return text
        label = self.decode(label)
        return text, label

    def add_special_char(self, dict_character):
        dict_character = ['blank'] + dict_character
        return dict_character


class CharacterOps(object):
    """ Convert between text-label and text-index """

    def __init__(self, config):
        self.character_type = config['character_type']
        self.loss_type = config['loss_type']
        if self.character_type == "en":
            self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
            dict_character = list(self.character_str)
        elif self.character_type == "ch":
            character_dict_path = config['character_dict_path']
            self.character_str = ""
            with open(character_dict_path, "rb") as fin:
                lines = fin.readlines()
                for line in lines:
                    line = line.decode('utf-8').strip("\n").strip("\r\n")
                    self.character_str += line
            dict_character = list(self.character_str)
        elif self.character_type == "en_sensitive":
            # same with ASTER setting (use 94 char).
            self.character_str = string.printable[:-6]
            dict_character = list(self.character_str)
        else:
            self.character_str = None
        assert self.character_str is not None, \
            "Nonsupport type of the character: {}".format(self.character_str)
        self.beg_str = "sos"
        self.end_str = "eos"
        if self.loss_type == "attention":
            dict_character = [self.beg_str, self.end_str] + dict_character
        self.dict = {}
        for i, char in enumerate(dict_character):
            self.dict[char] = i
        self.character = dict_character

    def encode(self, text):
        """convert text-label into text-index.
        input:
            text: text labels of each image. [batch_size]

        output:
            text: concatenated text index for CTCLoss.
                    [sum(text_lengths)] = [text_index_0 + text_index_1 + ... + text_index_(n - 1)]
            length: length of each text. [batch_size]
        """
        if self.character_type == "en":
            text = text.lower()

        text_list = []
        for char in text:
            if char not in self.dict:
                continue
            text_list.append(self.dict[char])
        text = np.array(text_list)
        return text

    def decode(self, text_index, is_remove_duplicate=False):
        """ convert text-index into text-label. """
        char_list = []
        char_num = self.get_char_num()

        if self.loss_type == "attention":
            beg_idx = self.get_beg_end_flag_idx("beg")
            end_idx = self.get_beg_end_flag_idx("end")
            ignored_tokens = [beg_idx, end_idx]
        else:
            ignored_tokens = [char_num]

        for idx in range(len(text_index)):
            if text_index[idx] in ignored_tokens:
                continue
            if is_remove_duplicate:
                if idx > 0 and text_index[idx - 1] == text_index[idx]:
                    continue
            char_list.append(self.character[text_index[idx]])
        text = ''.join(char_list)
        return text

    def get_char_num(self):
        return len(self.character)

    def get_beg_end_flag_idx(self, beg_or_end):
        if self.loss_type == "attention":
            if beg_or_end == "beg":
                idx = np.array(self.dict[self.beg_str])
            elif beg_or_end == "end":
                idx = np.array(self.dict[self.end_str])
            else:
                assert False, "Unsupport type %s in get_beg_end_flag_idx"\
                    % beg_or_end
            return idx
        else:
            err = "error in get_beg_end_flag_idx when using the loss %s"\
                % (self.loss_type)
            assert False, err


class OCRReader(object):
    def __init__(self,
                 algorithm="CRNN",
                 image_shape=[3, 32, 320],
                 char_type="ch",
                 batch_num=1,
                 char_dict_path="./ppocr_keys_v1.txt"):
        self.rec_image_shape = image_shape
        self.character_type = char_type
        self.rec_batch_num = batch_num
        char_ops_params = {}
        char_ops_params["character_type"] = char_type
        char_ops_params["character_dict_path"] = char_dict_path
        char_ops_params['loss_type'] = 'ctc'
        self.char_ops = CharacterOps(char_ops_params)
        self.label_ops = CTCLabelDecode(char_ops_params)

    def resize_norm_img(self, img, max_wh_ratio):
        imgC, imgH, imgW = self.rec_image_shape
        if self.character_type == "ch":
            imgW = int(32 * max_wh_ratio)
        h = img.shape[0]
        w = img.shape[1]
        ratio = w / float(h)
        if math.ceil(imgH * ratio) > imgW:
            resized_w = imgW
        else:
            resized_w = int(math.ceil(imgH * ratio))
        resized_image = cv2.resize(img, (resized_w, imgH))
        resized_image = resized_image.astype('float32')
        resized_image = resized_image.transpose((2, 0, 1)) / 255
        resized_image -= 0.5
        resized_image /= 0.5
        padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)

        padding_im[:, :, 0:resized_w] = resized_image
        return padding_im

    def preprocess(self, img_list):
        img_num = len(img_list)
        norm_img_batch = []
        max_wh_ratio = 0
        for ino in range(img_num):
            h, w = img_list[ino].shape[0:2]
            wh_ratio = w * 1.0 / h
            max_wh_ratio = max(max_wh_ratio, wh_ratio)

        for ino in range(img_num):
            norm_img = self.resize_norm_img(img_list[ino], max_wh_ratio)
            norm_img = norm_img[np.newaxis, :]
            norm_img_batch.append(norm_img)
        norm_img_batch = np.concatenate(norm_img_batch)
        norm_img_batch = norm_img_batch.copy()

        return norm_img_batch[0]

    def postprocess_old(self, outputs, with_score=False):
        rec_res = []
        rec_idx_lod = outputs["ctc_greedy_decoder_0.tmp_0.lod"]
        rec_idx_batch = outputs["ctc_greedy_decoder_0.tmp_0"]
        if with_score:
            predict_lod = outputs["softmax_0.tmp_0.lod"]
        for rno in range(len(rec_idx_lod) - 1):
            beg = rec_idx_lod[rno]
            end = rec_idx_lod[rno + 1]
            if isinstance(rec_idx_batch, list):
                rec_idx_tmp = [x[0] for x in rec_idx_batch[beg:end]]
            else:  #nd array
                rec_idx_tmp = rec_idx_batch[beg:end, 0]
            preds_text = self.char_ops.decode(rec_idx_tmp)
            if with_score:
                beg = predict_lod[rno]
                end = predict_lod[rno + 1]
                if isinstance(outputs["softmax_0.tmp_0"], list):
                    outputs["softmax_0.tmp_0"] = np.array(outputs[
                        "softmax_0.tmp_0"]).astype(np.float32)
                probs = outputs["softmax_0.tmp_0"][beg:end, :]
                ind = np.argmax(probs, axis=1)
                blank = probs.shape[1]
                valid_ind = np.where(ind != (blank - 1))[0]
                score = np.mean(probs[valid_ind, ind[valid_ind]])
                rec_res.append([preds_text, score])
            else:
                rec_res.append([preds_text])
        return rec_res

    def postprocess(self, outputs, with_score=False):
        preds = outputs["save_infer_model/scale_0.tmp_1"]
        try:
            preds = preds.numpy()
        except:
            pass
        preds_idx = preds.argmax(axis=2)
        preds_prob = preds.max(axis=2)
        text = self.label_ops.decode(
            preds_idx, preds_prob, is_remove_duplicate=True)
        return text